Addressing Bias in LLMs: Strategies and Application to Fair AI-based Recruitment

• URL: http://arxiv.org/abs/2506.11880v1
• Date: Fri, 13 Jun 2025 15:29:43 GMT
• Title: Addressing Bias in LLMs: Strategies and Application to Fair AI-based Recruitment
• Authors: Alejandro Peña, Julian Fierrez, Aythami Morales, Gonzalo Mancera, Miguel Lopez, Ruben Tolosana,
• Abstract summary: This work seeks to analyze the capacity of Transformers-based systems to learn demographic biases present in the data.<n>We propose a privacy-enhancing framework to reduce gender information from the learning pipeline as a way to mitigate biased behaviors in the final tools.
• Score: 49.81946749379338
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The use of language technologies in high-stake settings is increasing in recent years, mostly motivated by the success of Large Language Models (LLMs). However, despite the great performance of LLMs, they are are susceptible to ethical concerns, such as demographic biases, accountability, or privacy. This work seeks to analyze the capacity of Transformers-based systems to learn demographic biases present in the data, using a case study on AI-based automated recruitment. We propose a privacy-enhancing framework to reduce gender information from the learning pipeline as a way to mitigate biased behaviors in the final tools. Our experiments analyze the influence of data biases on systems built on two different LLMs, and how the proposed framework effectively prevents trained systems from reproducing the bias in the data.

Related papers

• Information Gain-Guided Causal Intervention for Autonomous Debiasing Large Language Models [40.853803921563596]
  Current large language models (LLMs) may still capture dataset biases and utilize them during inference.<n>We propose an information gain-guided causal intervention debiasing framework.<n>ICD can effectively debias LLM to improve its generalizability across different tasks.
  arXiv  Detail & Related papers  (2025-04-17T12:39:25Z)
• Detecting and Mitigating Bias in LLMs through Knowledge Graph-Augmented Training [2.8402080392117757]
  This work investigates Knowledge Graph-Augmented Training (KGAT) as a novel method to mitigate bias in large language models.<n>Public datasets for bias assessment include Gender Shades, Bias in Bios, and FairFace.<n>We also performed targeted mitigation strategies to correct biased associations, leading to a significant drop in biased output and improved bias metrics.
  arXiv  Detail & Related papers  (2025-04-01T00:27:50Z)
• Bias in Large Language Models: Origin, Evaluation, and Mitigation [4.606140332500086]
  Large Language Models (LLMs) have revolutionized natural language processing, but their susceptibility to biases poses significant challenges. This comprehensive review examines the landscape of bias in LLMs, from its origins to current mitigation strategies. Ethical and legal implications of biased LLMs are discussed, emphasizing potential harms in real-world applications such as healthcare and criminal justice.
  arXiv  Detail & Related papers  (2024-11-16T23:54:53Z)
• Cognitive Biases in Large Language Models for News Recommendation [68.90354828533535]
  This paper explores the potential impact of cognitive biases on large language models (LLMs) based news recommender systems. We discuss strategies to mitigate these biases through data augmentation, prompt engineering and learning algorithms aspects.
  arXiv  Detail & Related papers  (2024-10-03T18:42:07Z)
• Causal-Guided Active Learning for Debiasing Large Language Models [40.853803921563596]
  Current generative large language models (LLMs) may still capture dataset biases and utilize them for generation. Previous prior-knowledge-based debiasing methods and fine-tuning-based debiasing methods may not be suitable for current LLMs. We propose a casual-guided active learning framework, which utilizes LLMs itself to automatically and autonomously identify informative biased samples and induce the bias patterns.
  arXiv  Detail & Related papers  (2024-08-23T09:46:15Z)
• Unboxing Occupational Bias: Grounded Debiasing of LLMs with U.S. Labor Data [9.90951705988724]
  Large Language Models (LLM) are prone to inheriting and amplifying societal biases. LLM bias can have far-reaching consequences, leading to unfair practices and exacerbating social inequalities.
  arXiv  Detail & Related papers  (2024-08-20T23:54:26Z)
• Social Debiasing for Fair Multi-modal LLMs [55.8071045346024]
  Multi-modal Large Language Models (MLLMs) have advanced significantly, offering powerful vision-language understanding capabilities. However, these models often inherit severe social biases from their training datasets, leading to unfair predictions based on attributes like race and gender. This paper addresses the issue of social biases in MLLMs by i) Introducing a comprehensive Counterfactual dataset with Multiple Social Concepts (CMSC) and ii) Proposing an Anti-Stereotype Debiasing strategy (ASD)
  arXiv  Detail & Related papers  (2024-08-13T02:08:32Z)
• The Frontier of Data Erasure: Machine Unlearning for Large Language Models [56.26002631481726]
  Large Language Models (LLMs) are foundational to AI advancements. LLMs pose risks by potentially memorizing and disseminating sensitive, biased, or copyrighted information. Machine unlearning emerges as a cutting-edge solution to mitigate these concerns.
  arXiv  Detail & Related papers  (2024-03-23T09:26:15Z)
• ChatGPT Based Data Augmentation for Improved Parameter-Efficient Debiasing of LLMs [65.9625653425636]
  Large Language models (LLMs) exhibit harmful social biases. This work introduces a novel approach utilizing ChatGPT to generate synthetic training data.
  arXiv  Detail & Related papers  (2024-02-19T01:28:48Z)
• Bias and Fairness in Large Language Models: A Survey [73.87651986156006]
  We present a comprehensive survey of bias evaluation and mitigation techniques for large language models (LLMs) We first consolidate, formalize, and expand notions of social bias and fairness in natural language processing. We then unify the literature by proposing three intuitive, two for bias evaluation, and one for mitigation.
  arXiv  Detail & Related papers  (2023-09-02T00:32:55Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.